Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A data processing system comprising: a memory device configured to perform an operation corresponding to a command transferred from a memory controller, and output a memory data; a data collecting device configured to collect big data by capturing the command and the memory data transferred between the memory device and the memory controller in real time and combining/integrating captured data at a predetermined time period or at every predetermined time, split the collected big data based on a predetermined unit, and transfer the split big data; and a data processing device configured to store the split big data received from the data collecting device in block-based files in a High-Availability Distributed Object-Oriented Platform (HADOOP) distributed file system (HDFS), classify the block-based files based on a particular memory command, and process the block-based files.
2. The data processing system of claim 1 , wherein the particular memory command is selected from commands capable of detecting whether a memory device is in an operation state or in an idle state.
This technical summary describes a data processing system designed to monitor the operational state of memory devices, addressing inefficiencies in power management and performance optimization. The system includes a memory controller that executes specific memory commands to determine whether a memory device is in an active operation state or an idle state. These commands are selected from a set of commands capable of detecting the operational status of the memory device, enabling the system to dynamically adjust power consumption and resource allocation based on real-time usage patterns. By identifying idle states, the system can reduce unnecessary power draw, while recognizing active states ensures timely data processing without delays. This functionality enhances energy efficiency and system responsiveness, particularly in environments where memory devices frequently transition between active and idle states. The memory controller may also include additional logic to interpret the results of these detection commands and trigger appropriate actions, such as power gating or frequency scaling, to optimize overall system performance. This approach mitigates the problem of static power management strategies that fail to adapt to varying workload demands, leading to either excessive energy consumption or degraded performance. The system is applicable in computing devices, servers, and embedded systems where efficient memory management is critical.
3. The data processing system of claim 1 , wherein the particular memory command includes a refresh command.
A data processing system is designed to manage memory operations, particularly focusing on optimizing refresh commands in memory devices. The system includes a memory controller that generates and executes memory commands, including refresh commands, to maintain data integrity in volatile memory such as DRAM. The refresh command is a specific type of memory command that periodically restores charge levels in memory cells to prevent data loss due to leakage. The system may also include a memory device that receives and processes these commands, ensuring proper timing and execution to sustain reliable memory operations. The memory controller may further include logic to determine when to issue refresh commands based on factors like memory usage patterns, temperature, or other operational conditions. This approach helps balance performance and power efficiency while ensuring data retention. The system may be integrated into computing devices, servers, or embedded systems where memory reliability is critical. The focus on refresh commands addresses the challenge of maintaining data integrity in volatile memory without excessive power consumption or performance degradation.
4. The data processing system of claim 3 , wherein the particular memory command includes an all-bank refresh command for refreshing all banks.
A data processing system is designed to manage memory operations efficiently, particularly in systems with multiple memory banks. The system includes a memory controller that processes memory commands, including commands for refreshing memory banks to maintain data integrity. A key feature is the ability to handle an all-bank refresh command, which simultaneously refreshes all memory banks in the system. This command ensures that all banks are refreshed in a coordinated manner, reducing the risk of data corruption due to unrefreshed memory cells. The system may also include mechanisms to prioritize or schedule refresh operations based on system requirements, ensuring optimal performance and reliability. By supporting all-bank refresh commands, the system improves memory management in high-performance computing environments where multiple memory banks are active. This approach minimizes latency and power consumption associated with individual bank refreshes, enhancing overall system efficiency. The system is particularly useful in applications requiring high-speed data processing and reliable memory access, such as servers, data centers, and embedded systems.
5. The data processing system of claim 3 , wherein the particular memory command includes a per-bank refresh command for refreshing an individual bank among banks and a target bank address corresponding to the individual bank to be refreshed.
A data processing system is designed to manage memory operations in a memory device, particularly focusing on efficient refresh operations. The system addresses the challenge of optimizing memory refresh processes to improve performance and reduce power consumption. The system includes a memory controller that generates and executes specific memory commands to control the refresh operations of a memory device. One such command is a per-bank refresh command, which targets a specific bank within the memory device for refresh rather than refreshing all banks simultaneously. This selective refresh approach allows for more granular control over memory maintenance, reducing unnecessary refresh cycles and conserving power. The per-bank refresh command includes a target bank address that identifies the individual bank to be refreshed, ensuring precise and efficient memory management. By implementing this targeted refresh mechanism, the system enhances memory performance and energy efficiency, particularly in applications where memory usage is dynamic and varies across different banks. The memory controller dynamically selects which banks require refresh based on usage patterns, further optimizing system performance. This approach is particularly beneficial in high-density memory systems where power consumption and thermal management are critical considerations.
6. The data processing system of claim 3 , wherein the data processing device divides the stored block-based files into data sets of a preset unit by parsing the refresh command by a clock unit, analyzes the data sets by using a command counter algorithm, an illegal check algorithm, an asynchronous analysis algorithm, a power analysis algorithm, and a smart search algorithm, and summarizes analysis results to output a summarized result.
This invention relates to a data processing system designed to analyze stored block-based files for errors, security vulnerabilities, and performance optimization. The system addresses the challenge of efficiently processing large volumes of block-based data, such as those stored in databases or file systems, to detect anomalies, illegal operations, power consumption issues, and other critical factors that may impact system reliability and security. The data processing device divides the stored block-based files into smaller data sets of a predefined unit size. This division is performed by parsing a refresh command using a clock unit, ensuring synchronized and periodic analysis. Each data set is then subjected to multiple analytical algorithms, including a command counter algorithm to track and validate command execution, an illegal check algorithm to detect unauthorized or malicious operations, an asynchronous analysis algorithm to identify timing-related inconsistencies, a power analysis algorithm to monitor and optimize energy consumption, and a smart search algorithm to efficiently locate specific data patterns or anomalies. The results from these analyses are consolidated into a summarized output, providing a comprehensive overview of the system's health, security, and performance. This approach enables proactive maintenance, threat detection, and resource optimization in data-intensive environments.
7. The data processing system of claim 6 , wherein the data processing device searches for the refresh command from an initial position of the stored block-based files, puts a clock-based parser at every position where the refresh command is searched, and divides the block-based files into the data sets based on positions where the clock-based parser is put.
This invention relates to a data processing system for managing block-based files, particularly focusing on efficiently locating and processing refresh commands within these files. The system addresses the challenge of identifying and parsing refresh commands in large, structured data files to enable efficient data updates or synchronization. The data processing device searches for refresh commands starting from the initial position of the stored block-based files. Upon detecting a refresh command, the system places a clock-based parser at that position. The clock-based parser is used to segment the block-based files into distinct data sets based on the positions where the parsers are placed. This segmentation allows for targeted processing of the data sets, improving data management and reducing unnecessary computations. The system ensures that refresh commands are accurately identified and processed, enabling efficient updates or synchronization of the data sets within the block-based files. The use of clock-based parsing further optimizes the processing by aligning the segmentation with time-based or sequential data structures, enhancing performance in applications requiring real-time or periodic data updates.
8. The data processing system of claim 1 , wherein the data processing device includes: the HDFS configured to divide the split big data into the block-based files of a predetermined size, and store the block-based files; and a Map-Reducer configured to divide data stored in the block-based files of the HDFS into data sets of a preset unit by parsing the data by the particular memory command, and process the data sets in parallel based on a Map-Reduce scheme.
This invention relates to a data processing system designed for handling large-scale data, often referred to as big data. The system addresses the challenge of efficiently storing and processing massive datasets by leveraging distributed storage and parallel processing techniques. The system includes a distributed file system, specifically the Hadoop Distributed File System (HDFS), which divides big data into smaller, block-based files of a predetermined size. These files are then stored across multiple nodes in a distributed manner, ensuring fault tolerance and scalability. The system also incorporates a Map-Reducer, which processes the stored data in parallel using the Map-Reduce framework. The Map-Reducer parses the data from the block-based files into smaller datasets of a preset unit, guided by a particular memory command. These datasets are then processed in parallel, significantly improving processing speed and efficiency. The combination of distributed storage and parallel processing allows the system to handle large-scale data operations, such as sorting, filtering, and aggregation, with high performance. This approach is particularly useful in environments where data volumes are too large for traditional single-node processing systems. The system ensures that data is processed in a scalable and fault-tolerant manner, making it suitable for big data analytics and other data-intensive applications.
9. The data processing system of claim 8 , wherein the Map-Reducer includes: a first Map-Reducer (MR) module configured to index the data stored in the block-based files of the HDFS by a small unit, distributively process the indexed data based on the Map-Reduce scheme, and output a merged file; and a second MR module configured to divide the merged file into data sets of the preset unit by parsing the merged file by the particular memory command, analyze the data sets, and summarize analysis results to output a summarized result.
The invention relates to a data processing system for efficiently analyzing large datasets stored in a distributed file system, such as the Hadoop Distributed File System (HDFS). The system addresses the challenge of processing and summarizing large-scale data stored in block-based files, which can be computationally intensive and inefficient when handled by traditional methods. The system includes a Map-Reducer component that processes data in two stages. The first stage involves a Map-Reducer (MR) module that indexes the data stored in the block-based files of the HDFS at a granular level, then distributively processes the indexed data using the Map-Reduce scheme. This stage outputs a merged file containing the processed data. The second stage involves another MR module that divides the merged file into smaller data sets of a predefined unit by parsing the file using a specific memory command. This module then analyzes these data sets and summarizes the analysis results, producing a final summarized output. By breaking down the processing into these two stages, the system improves efficiency and scalability, allowing for faster and more manageable data analysis in distributed environments. The use of Map-Reduce ensures parallel processing, while the division of the merged file into smaller units optimizes memory usage and processing speed. This approach is particularly useful for applications requiring large-scale data analytics, such as big data processing, machine learning, and distributed computing tasks.
10. The data processing system of claim 9 , wherein the first MR module includes: a first mapper configured to perform a mapping operation of dividing the data stored in the block-based files of the HDFS into data of the small unit, and index the data of the small unit in a form of <KEY, VALUE>; and a first reducer configured to receive indexed data from the first mapper, shuffle and sort the indexed data of the same key value, and perform a reducing operation of generating the merged file by merging the shuffled and sorted data.
The invention relates to a data processing system for efficiently handling large-scale data stored in block-based files within a distributed file system, such as the Hadoop Distributed File System (HDFS). The system addresses the challenge of processing and analyzing large datasets by breaking them into smaller, manageable units and performing distributed computations to generate merged output files. The system includes a first MapReduce (MR) module designed to process data stored in block-based files. The MR module comprises a mapper and a reducer. The mapper performs a mapping operation that divides the data stored in the HDFS into smaller units and indexes these units in a key-value pair format (<KEY, VALUE>). The reducer then receives the indexed data from the mapper, shuffles and sorts the data based on the same key values, and performs a reducing operation to merge the shuffled and sorted data into a single merged file. This process enables efficient data aggregation and transformation, improving the performance of large-scale data processing tasks. The system leverages distributed computing principles to handle data-intensive operations, ensuring scalability and reliability in processing large datasets.
11. The data processing system of claim 9 , wherein the second MR module includes: an input formatter configured to divide the merged file into the data sets by parsing the merged file by the particular memory command; a second mapper configured to analyze the data sets by using a command counter algorithm, an illegal check algorithm, an asynchronous (AC) analysis algorithm, a power analysis algorithm, and a smart search algorithm; and a second reducer configured to summarize analysis results of the second mapper to output the summarized result.
This invention relates to a data processing system for analyzing memory commands in a merged file containing multiple data sets. The system addresses the challenge of efficiently processing and analyzing large volumes of memory command data to detect errors, inconsistencies, or security vulnerabilities. The system includes a second memory read (MR) module that processes the merged file by dividing it into individual data sets based on specific memory commands. The input formatter parses the merged file to separate the data sets according to the memory command structure. A second mapper then analyzes each data set using multiple algorithms: a command counter algorithm to track command occurrences, an illegal check algorithm to identify invalid commands, an asynchronous (AC) analysis algorithm to detect timing-related issues, a power analysis algorithm to assess power consumption patterns, and a smart search algorithm to locate specific data patterns or anomalies. The second reducer consolidates the analysis results from the mapper into a summarized output, providing a comprehensive overview of the memory command data. This system enhances memory command analysis by automating error detection and improving efficiency in large-scale data processing.
12. The data processing system of claim 11 , wherein the input formatter searches for a refresh command from an initial position of the merged file, puts a clock-based parser at every position where the particular memory command is searched, and divides the merged file into the data sets based on positions where the clock-based parser is put.
The invention relates to a data processing system designed to efficiently handle memory commands within a merged file. The system addresses the challenge of processing large files containing mixed data and commands, particularly focusing on identifying and executing refresh commands to maintain memory integrity. The input formatter scans the merged file starting from its initial position to locate refresh commands. Upon detecting a refresh command, the system places a clock-based parser at that position. This parser is used to search for specific memory commands within the file. The merged file is then divided into distinct data sets based on the positions where the clock-based parsers are placed. This segmentation allows for organized and efficient processing of the data, ensuring that memory operations are executed in the correct sequence. The system enhances performance by reducing the need for repeated scans and optimizing the handling of memory-related commands within the file.
13. A data processing method comprising: outputting a memory data by a memory device by performing an operation corresponding to a command transferred from a memory controller; collecting big data by capturing the command and the memory data transferred between the memory device and the memory controller in real time and combining/integrating captured data at a predetermined time period or at every predetermined time, and transferring the collected big data by splitting the collected big data into a predetermined unit; and storing the big data in block-based files in a High-Availability Distributed Object-Oriented Platform (HADOOP) distributed file system (HDFS), dividing the stored block-based files by a particular memory command, and processing the divided block-based files.
This invention relates to a data processing method for monitoring and analyzing memory operations in a system where a memory controller interacts with a memory device. The method addresses the challenge of efficiently capturing, storing, and processing large volumes of memory-related data to enable real-time or periodic analysis of memory behavior. The method involves a memory device outputting data in response to commands from a memory controller. A monitoring system captures these commands and the corresponding memory data in real time, aggregating the captured data at predefined intervals or after a set number of operations. The collected data is then split into predetermined units for transfer. The transferred data is stored in block-based files within a Hadoop Distributed File System (HDFS), a distributed storage platform designed for high availability and scalability. The stored files are further divided based on specific memory commands, allowing for structured processing of the segmented data. This segmentation enables efficient analysis of memory operations, such as identifying patterns, detecting anomalies, or optimizing performance. The method ensures that large-scale memory data is managed in a distributed and fault-tolerant manner, facilitating big data analytics in memory systems.
14. The data processing method of claim 13 , wherein the particular memory command includes a refresh command.
A data processing method is disclosed for managing memory operations in a computing system, particularly addressing the challenge of efficiently handling memory refresh operations to maintain data integrity while optimizing performance. The method involves executing a particular memory command, which in this case is a refresh command, to refresh memory cells in a memory device. The refresh command is issued to prevent data loss due to leakage or decay in dynamic memory cells, ensuring reliable data retention. The method may also include determining whether to execute the refresh command based on certain conditions, such as elapsed time, memory usage patterns, or system performance metrics. By dynamically adjusting refresh operations, the method aims to balance data integrity with system efficiency, reducing unnecessary refresh cycles that could otherwise degrade performance. The technique is applicable to various memory types, including dynamic random-access memory (DRAM), where periodic refreshes are essential for maintaining stored data. The method may be implemented in memory controllers, processors, or other components responsible for managing memory operations in computing systems.
15. The data processing method of claim 14 , wherein the particular memory command includes an all-bank refresh command for refreshing all banks.
This invention relates to data processing methods for memory systems, specifically addressing the need for efficient memory refresh operations in multi-bank memory architectures. The method involves executing a particular memory command that targets all memory banks simultaneously, rather than refreshing banks individually. This all-bank refresh command ensures uniform refresh timing across all memory banks, reducing latency and improving system performance by eliminating the need for sequential refresh operations. The method is particularly useful in high-performance computing environments where minimizing refresh overhead is critical. The invention also includes mechanisms to handle the all-bank refresh command in a way that avoids conflicts with other memory operations, ensuring data integrity and system stability. By refreshing all banks at once, the method optimizes memory access efficiency and reduces power consumption compared to traditional per-bank refresh approaches. The invention is applicable to dynamic random-access memory (DRAM) systems and other memory architectures requiring periodic refresh cycles to maintain data retention.
16. The data processing method of claim 14 , wherein the particular memory command includes a per-bank refresh command for refreshing an individual bank among banks and a target bank address corresponding to the individual bank to be refreshed.
The invention relates to memory systems, specifically methods for managing memory refresh operations in a memory device. The problem addressed is the inefficiency of conventional refresh operations that refresh all memory banks simultaneously, leading to unnecessary power consumption and performance degradation. The invention provides a more efficient refresh mechanism by allowing selective refresh of individual memory banks. The method involves issuing a particular memory command that includes a per-bank refresh command and a target bank address. The per-bank refresh command specifies that only a single bank among multiple banks in the memory device should be refreshed, rather than refreshing all banks at once. The target bank address identifies the specific bank to be refreshed, enabling precise control over which memory regions are refreshed. This selective refresh approach reduces power consumption by avoiding unnecessary refresh operations on banks that do not require refreshing. Additionally, it improves system performance by minimizing disruptions to other memory operations that may be occurring in non-refreshed banks. The method may also include determining whether a refresh operation is needed for a particular bank based on factors such as usage patterns or error rates, and dynamically adjusting refresh intervals for different banks to optimize efficiency. This adaptive approach ensures that only banks requiring refresh are targeted, further enhancing energy efficiency and performance. The invention is particularly useful in memory systems where power efficiency and performance are critical, such as in mobile devices or high-performance computing environments.
17. The data processing method of claim 13 , wherein the storing of the big data in the block-based files in the HDFS, the dividing of the stored block-based files by the particular memory command, and the processing of the divided block-based files includes: dividing the big data into the block-based files of a predetermined size and storing the block-based files in the HDFS; indexing data stored in the block-based files of the HDFS by a small unit, distributively processing the indexed data based on a Map-Reduce scheme, and outputting a merged file; and dividing the merged file into data sets of a preset unit by parsing the merged file by the particular memory command, analyzing the data sets, and summarizing analysis results to output a summarized result.
This invention relates to a data processing method for efficiently handling big data in a distributed storage system, specifically addressing challenges in storing, indexing, and analyzing large datasets in a scalable and resource-efficient manner. The method involves storing big data as block-based files in a Hadoop Distributed File System (HDFS), where the data is divided into fixed-size blocks for distributed storage. The stored block-based files are then indexed at a granular level to facilitate distributed processing. Using a Map-Reduce framework, the indexed data is processed in parallel across multiple nodes, generating a merged output file. This merged file is further divided into smaller data sets by parsing it with a specific memory command, which allows for detailed analysis of the data sets. The analysis results are then summarized and output as a final result. The method optimizes data handling by leveraging distributed computing and efficient file partitioning, ensuring scalable and efficient big data processing.
18. The data processing method of claim 17 , wherein the outputting of the merged file includes: performing a mapping operation of dividing the data stored in the block-based files of the HDFS into data of the small unit and indexing the data of the small unit in a form of <KEY, VALUE>; receiving the indexed data, and shuffling and sorting data of the same key value; and performing a reducing operation of generating the merged file by merging the shuffled and sorted data.
This invention relates to data processing in distributed file systems, specifically addressing the challenge of efficiently merging multiple block-based files stored in a Hadoop Distributed File System (HDFS) into a single merged file. The method involves dividing the data stored in these block-based files into smaller units, indexing the data in a key-value format, and then shuffling and sorting the data based on key values. After sorting, a reducing operation is performed to merge the shuffled and sorted data into a final merged file. The process ensures that data from different files is properly organized and consolidated, improving data accessibility and processing efficiency in distributed computing environments. The method leverages distributed computing principles to handle large-scale data merging tasks, reducing the complexity and time required for data consolidation in HDFS.
19. The data processing method of claim 17 , wherein the summarizing of the analysis results to output the summarized result includes: dividing the merged file into the data sets by parsing the merged file by the particular memory command; analyzing the data sets by using a command counter algorithm, an illegal check algorithm, an asynchronous (AC) analysis algorithm, a power analysis algorithm, and a smart search algorithm; and summarizing the analysis results to output the summarized result.
This invention relates to data processing methods for analyzing memory operations, particularly in systems where multiple memory commands are executed and their results need to be summarized efficiently. The problem addressed is the need to parse and analyze merged memory operation data to identify errors, inefficiencies, or security vulnerabilities while providing a concise summary of the findings. The method involves processing a merged file containing memory commands by dividing it into smaller data sets. Each data set is parsed using a specific memory command to isolate relevant segments for analysis. The analysis is performed using multiple algorithms: a command counter algorithm to track memory operations, an illegal check algorithm to detect invalid commands, an asynchronous (AC) analysis algorithm to evaluate timing and synchronization issues, a power analysis algorithm to assess energy consumption, and a smart search algorithm to identify patterns or anomalies. The results from these analyses are then compiled into a summarized output, providing a high-level overview of the memory operations' performance, security, and efficiency. This approach ensures comprehensive analysis while reducing the complexity of interpreting raw data.
20. The data processing method of claim 19 , wherein the dividing of the merged file into the data sets includes: searching for a refresh command from an initial position of the merged file; and putting a clock-based parser at every position where the refresh command is searched, and dividing the merged file into the data sets based on positions where the clock-based parser is put.
This invention relates to data processing methods for handling merged files containing multiple data sets, particularly in systems where data is periodically refreshed. The problem addressed is efficiently dividing a merged file into its constituent data sets, especially when the file contains refresh commands that mark boundaries between data sets. The method involves analyzing the merged file to locate refresh commands starting from the initial position. A clock-based parser is then placed at each detected refresh command position. The merged file is subsequently divided into data sets based on these parser positions, ensuring accurate segmentation of the data. The clock-based parser likely synchronizes with time-based data structures within the file, allowing precise identification of data set boundaries. This approach is useful in applications requiring real-time data processing, such as financial transactions, sensor data logging, or time-series analysis, where maintaining data integrity and temporal accuracy is critical. The method ensures that each data set is correctly isolated, preventing data corruption or misalignment during processing. The technique may be implemented in software or hardware systems handling large volumes of time-stamped data, improving efficiency and reliability in data management.
21. A data processing system comprising: a memory device configured to perform an operation corresponding to a command transferred from a memory controller, and output a memory data; a data collecting device configured to collect big data by capturing the command and the memory data transferred between the memory device and the memory controller in real time and combining/integrating captured data at a predetermined time period or at every predetermined time, and transfer the collected big data by splitting the collected big data into a predetermined unit; and a data processing device configured to distributively store the big data transferred from the data collecting device in block-based files, divide the stored block-based files by a particular memory command, and parallel process the divided block-based files.
The invention relates to a data processing system designed to monitor and analyze memory operations in real-time, particularly for big data applications. The system addresses the challenge of efficiently capturing, storing, and processing large volumes of memory-related data generated during interactions between a memory device and a memory controller. Traditional systems often struggle with the sheer volume and complexity of this data, leading to inefficiencies in analysis and storage. The system includes a memory device that executes commands from a memory controller and outputs memory data. A data collecting device captures these commands and the corresponding memory data in real-time, aggregating the captured data at predetermined intervals or frequencies. The collected data is then split into predefined units for transfer. A data processing device receives this data, storing it in block-based files distributed across a storage system. These files are further divided based on specific memory commands, enabling parallel processing of the segmented data. This approach enhances scalability and performance by distributing the computational load across multiple processing units. The system is particularly useful in environments requiring high-speed data analysis, such as real-time monitoring of memory operations in large-scale computing systems.
22. The data processing system of claim 21 , wherein the data processing device divides the stored block-based files into data sets of a preset unit by parsing a refresh command.
This invention relates to a data processing system designed to optimize the handling of block-based files, particularly in scenarios requiring efficient data management and retrieval. The system addresses the challenge of managing large volumes of block-based files, which are commonly used in storage systems, databases, and file systems. These files are typically divided into fixed-size blocks, but traditional methods of accessing and updating them can be inefficient, leading to performance bottlenecks and increased storage overhead. The data processing system includes a data processing device that enhances file management by dividing stored block-based files into smaller, more manageable data sets of a preset unit. This division is triggered by parsing a refresh command, which instructs the system to reorganize the files into these optimized data sets. The preset unit can be defined based on factors such as file size, access patterns, or storage constraints, allowing for flexible and adaptive data organization. By breaking down large files into smaller, uniform data sets, the system improves data retrieval speed, reduces storage fragmentation, and simplifies file maintenance tasks. Additionally, the system may include features for tracking metadata associated with the data sets, ensuring that the division process preserves data integrity and relationships between blocks. The refresh command can be issued manually or automatically, depending on system requirements, and the division process may involve reindexing or reorganizing the data sets to maintain optimal performance. This approach is particularly useful in environments where files are frequently updated or accessed, such as in database systems, cloud storage, or distributed file systems. The invention provides
23. The data processing system of claim 22 , wherein the data processing device searches for the refresh command from an initial position of the stored block-based files, puts a clock-based parser at every position where the refresh command is searched, and divides the block-based files into the data sets based on positions where the clock-based parser is put.
This invention relates to a data processing system for managing block-based files, particularly focusing on efficiently locating and processing refresh commands within these files. The system addresses the challenge of identifying and parsing refresh commands in large, structured data files, which is critical for maintaining data consistency and integrity in storage systems. The data processing system includes a data processing device configured to search for refresh commands within stored block-based files. The search begins at an initial position within the files, ensuring systematic scanning. Upon detecting a refresh command, the system places a clock-based parser at that position. This parser is used to segment the block-based files into distinct data sets based on the locations where the refresh commands are found. The clock-based parser ensures that the division of data is synchronized with the timing of the refresh commands, allowing for precise and efficient data management. The system further includes a storage device for storing the block-based files and a communication interface for transmitting the divided data sets to other components or systems. The clock-based parser may also be configured to generate metadata associated with the data sets, which can include timestamps or other identifiers to facilitate tracking and retrieval. This approach enhances data processing efficiency by automating the segmentation of files based on refresh commands, reducing manual intervention and potential errors. The system is particularly useful in environments where real-time data updates and consistency are critical, such as in database management or file storage systems.
24. The data processing system of claim 22 , wherein the data processing device analyzes the data sets by using a command counter algorithm, an illegal check algorithm, an asynchronous analysis algorithm, a power analysis algorithm, and a smart search algorithm, and summarizes analysis results to output a summarized result.
This invention relates to a data processing system designed to analyze and summarize data sets using multiple specialized algorithms. The system addresses the challenge of efficiently processing large volumes of data by employing a combination of analytical techniques to extract meaningful insights. The data processing device within the system utilizes a command counter algorithm to track and quantify specific commands or operations within the data. An illegal check algorithm identifies and flags any unauthorized or invalid operations, ensuring data integrity. An asynchronous analysis algorithm processes data streams in parallel or out-of-order sequences, improving efficiency in handling real-time or high-throughput data. A power analysis algorithm assesses the computational or energy consumption patterns associated with data processing tasks, optimizing resource usage. Additionally, a smart search algorithm enhances data retrieval by employing intelligent search techniques, such as pattern recognition or predictive modeling. The system integrates the results from these algorithms into a summarized output, providing a consolidated overview of the analyzed data. This approach enables comprehensive data monitoring, security validation, and performance optimization in various applications, including cybersecurity, system diagnostics, and operational analytics.
Unknown
February 11, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.